MemoGen: Can Past Experience Improve Future Text-to-Image Generation? 事件

MemoGen: Can Past Experience Improve Future Text-to-Image Generation? arXiv:2606.03243v1 Announce Type: new Abstract: Modern text-to-image models have achieved strong visual synthesis, yet remain unreliable when prompts require implicit visual constraints, relational reasoning, or external knowledge. Existing retrieval-augmented and agentic generation methods mitigate this issue by acquiring external knowledge, references, or refined prompts for the current request, yet they typically treat eac